RAM d850660872 [Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989) ...

* reset decoder_block_shape_q buffer

* refactor GetBlockShapeAndSplitKVBlock Kernel and cudagraph padding batch

* update decode_max_tile_size

* fix pre-commit

* update block_multihead_attn_backend

* update flas attn backend

* update MLA Attention

* update XPU Attention

* update gcu,iluvatar model runner

* Update MTP

* fix MTP bug

2025-07-31 00:09:31 +08:00

..

cpu_ops

…

gpu_ops

[Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989)

2025-07-31 00:09:31 +08:00

iluvatar_ops

refactor rl get_name_mappings_to_training (#2847)

2025-07-15 07:31:42 -07:00

utils

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

xpu_ops

[XPU] Support kvblock centralized management (#3017)

2025-07-29 10:40:55 +08:00

0001-DeepGEMM-95e81b3.patch

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

MANIFEST.in

…

setup_ops_base.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

setup_ops_cpu.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

setup_ops.py

[Feature] Multimodal Scheduler V1 (#3019)

2025-07-30 16:05:55 +08:00